agenteval-toolkit 0.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (67) hide show
  1. agenteval/__init__.py +5 -0
  2. agenteval/_starter/certification/policy.yaml +15 -0
  3. agenteval/_starter/certification/systems/northwind-cs-staging.yaml +16 -0
  4. agenteval/_starter/certification/systems/northwind-cs.yaml +17 -0
  5. agenteval/_starter/examples/agents/demo-good.yaml +41 -0
  6. agenteval/_starter/examples/agents/demo-weak.yaml +34 -0
  7. agenteval/_starter/examples/agents/openai-compatible.example.yaml +15 -0
  8. agenteval/_starter/examples/agents/webhook.example.yaml +21 -0
  9. agenteval/_starter/examples/attestations-certification.yaml +16 -0
  10. agenteval/_starter/examples/attestations.yaml +19 -0
  11. agenteval/_starter/examples/snapshots/sample-cluster.json +323 -0
  12. agenteval/_starter/exams/customer-service/cs-ecommerce-v1.yaml +222 -0
  13. agenteval/_starter/rules/industry-pci-dss/i18n/zh.yaml +27 -0
  14. agenteval/_starter/rules/industry-pci-dss/pack.yaml +9 -0
  15. agenteval/_starter/rules/industry-pci-dss/rules.yaml +83 -0
  16. agenteval/_starter/rules/us-ca/i18n/zh.yaml +21 -0
  17. agenteval/_starter/rules/us-ca/pack.yaml +9 -0
  18. agenteval/_starter/rules/us-ca/rules.yaml +72 -0
  19. agenteval/_starter/rules/us-federal/governance.yaml +216 -0
  20. agenteval/_starter/rules/us-federal/i18n/zh.yaml +107 -0
  21. agenteval/_starter/rules/us-federal/pack.yaml +8 -0
  22. agenteval/_starter/rules/us-federal/security.yaml +164 -0
  23. agenteval/certification/__init__.py +16 -0
  24. agenteval/certification/assess.py +137 -0
  25. agenteval/certification/issuer.py +165 -0
  26. agenteval/certification/models.py +113 -0
  27. agenteval/certification/render.py +100 -0
  28. agenteval/certification/signing.py +86 -0
  29. agenteval/cli.py +533 -0
  30. agenteval/collectors/__init__.py +30 -0
  31. agenteval/collectors/kubernetes.py +70 -0
  32. agenteval/collectors/normalize.py +247 -0
  33. agenteval/config.py +49 -0
  34. agenteval/engine/__init__.py +12 -0
  35. agenteval/engine/conditions.py +109 -0
  36. agenteval/engine/evaluator.py +133 -0
  37. agenteval/engine/loader.py +131 -0
  38. agenteval/evaluation/__init__.py +17 -0
  39. agenteval/evaluation/adapters.py +276 -0
  40. agenteval/evaluation/assertions.py +73 -0
  41. agenteval/evaluation/judges.py +214 -0
  42. agenteval/evaluation/messages.py +56 -0
  43. agenteval/evaluation/models.py +174 -0
  44. agenteval/evaluation/papers.py +103 -0
  45. agenteval/evaluation/report.py +80 -0
  46. agenteval/evaluation/runner.py +154 -0
  47. agenteval/i18n.py +118 -0
  48. agenteval/models.py +136 -0
  49. agenteval/reports/__init__.py +86 -0
  50. agenteval/reports/templates/certificate.html.j2 +178 -0
  51. agenteval/reports/templates/eval_report.html.j2 +191 -0
  52. agenteval/reports/templates/report.html.j2 +75 -0
  53. agenteval/schema.py +66 -0
  54. agenteval/schemas/attestations.schema.json +76 -0
  55. agenteval/schemas/exam.schema.json +85 -0
  56. agenteval/schemas/pack.schema.json +48 -0
  57. agenteval/schemas/policy.schema.json +67 -0
  58. agenteval/schemas/rule.schema.json +298 -0
  59. agenteval/schemas/system.schema.json +76 -0
  60. agenteval/schemas/translations.schema.json +32 -0
  61. agenteval_toolkit-0.1.0.dist-info/METADATA +307 -0
  62. agenteval_toolkit-0.1.0.dist-info/RECORD +67 -0
  63. agenteval_toolkit-0.1.0.dist-info/WHEEL +5 -0
  64. agenteval_toolkit-0.1.0.dist-info/entry_points.txt +2 -0
  65. agenteval_toolkit-0.1.0.dist-info/licenses/LICENSE +202 -0
  66. agenteval_toolkit-0.1.0.dist-info/licenses/NOTICE +19 -0
  67. agenteval_toolkit-0.1.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,307 @@
1
+ Metadata-Version: 2.4
2
+ Name: agenteval-toolkit
3
+ Version: 0.1.0
4
+ Summary: Scan AI infrastructure against policy-as-code rule packs, evaluate AI agents with standard exams, and issue signed certificates when both pass.
5
+ Author: The AgentEval Authors
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://github.com/pony360/AgentEval
8
+ Project-URL: Documentation, https://github.com/pony360/AgentEval/tree/main/docs
9
+ Project-URL: Source, https://github.com/pony360/AgentEval
10
+ Project-URL: Issues, https://github.com/pony360/AgentEval/issues
11
+ Project-URL: Changelog, https://github.com/pony360/AgentEval/blob/main/CHANGELOG.md
12
+ Keywords: ai-governance,compliance,policy-as-code,llm-evaluation,ai-agents,kubernetes,certification
13
+ Classifier: Development Status :: 3 - Alpha
14
+ Classifier: Environment :: Console
15
+ Classifier: Intended Audience :: Developers
16
+ Classifier: Intended Audience :: System Administrators
17
+ Classifier: Operating System :: OS Independent
18
+ Classifier: Programming Language :: Python :: 3
19
+ Classifier: Programming Language :: Python :: 3.11
20
+ Classifier: Programming Language :: Python :: 3.12
21
+ Classifier: Programming Language :: Python :: 3.13
22
+ Classifier: Topic :: Security
23
+ Classifier: Topic :: Software Development :: Quality Assurance
24
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
25
+ Requires-Python: >=3.11
26
+ Description-Content-Type: text/markdown
27
+ License-File: LICENSE
28
+ License-File: NOTICE
29
+ Requires-Dist: pydantic>=2.6
30
+ Requires-Dist: PyYAML>=6.0
31
+ Requires-Dist: jsonschema>=4.21
32
+ Requires-Dist: typer>=0.12
33
+ Requires-Dist: Jinja2>=3.1
34
+ Requires-Dist: httpx>=0.27
35
+ Requires-Dist: cryptography>=42
36
+ Requires-Dist: qrcode>=7.4
37
+ Provides-Extra: kubernetes
38
+ Requires-Dist: kubernetes>=29.0; extra == "kubernetes"
39
+ Provides-Extra: pdf
40
+ Requires-Dist: playwright>=1.44; extra == "pdf"
41
+ Provides-Extra: dev
42
+ Requires-Dist: pytest>=8.0; extra == "dev"
43
+ Requires-Dist: build>=1.2; extra == "dev"
44
+ Dynamic: license-file
45
+
46
+ # AgentEval
47
+
48
+ **Scan, evaluate, certify.** AgentEval is an Apache-2.0 command-line toolkit with three jobs:
49
+
50
+ - it **scans** self-hosted AI infrastructure against policy-as-code rule packs,
51
+ - it **evaluates** AI agents with standard exam papers, and
52
+ - it **issues signed certificates** when a system passes both.
53
+
54
+ [English](https://github.com/pony360/AgentEval/blob/main/README.md) · [简体中文](https://github.com/pony360/AgentEval/blob/main/README.zh-CN.md)
55
+
56
+ > **Status: alpha (0.1.0).** The rule packs are starter mappings, and every one is marked `verified: false`.
57
+ > They are a starting point for your own legal and compliance review. They are not legal advice.
58
+
59
+ ---
60
+
61
+ ## Contents
62
+
63
+ - [Why](#why)
64
+ - [Features](#features)
65
+ - [Install](#install)
66
+ - [Quickstart](#quickstart)
67
+ - [Commands and exit codes](#commands-and-exit-codes)
68
+ - [Rule packs](#rule-packs)
69
+ - [Writing rules](#writing-rules)
70
+ - [Evaluating agents](#evaluating-agents)
71
+ - [Certification](#certification)
72
+ - [Configuration](#configuration)
73
+ - [Security model](#security-model)
74
+ - [Project layout](#project-layout)
75
+ - [Roadmap](#roadmap)
76
+ - [Contributing](#contributing)
77
+ - [License](#license)
78
+
79
+ ## Why
80
+
81
+ Teams that run their own models on Kubernetes have to answer two separate questions:
82
+
83
+ - *Is the deployment configured the way our policies require?* (auth, TLS, provenance, PII handling, …)
84
+ - *Does the agent built on it do its job safely?* (task completion, accuracy, prompt-injection resistance, …)
85
+
86
+ AgentEval answers both with versioned, reviewable files, rules and exams in YAML, and turns the
87
+ combined result into a certificate that anyone can verify offline.
88
+
89
+ ## Features
90
+
91
+ | | |
92
+ |---|---|
93
+ | **Compliance scanning** | Live Kubernetes cluster or offline snapshot. Normalizes vLLM, TGI, Triton, Ollama, llama.cpp, SGLang, Ray Serve and KServe workloads into facts |
94
+ | **Policy-as-code** | YAML rules validated by JSON Schema. A safe, fail-closed condition DSL. Automated and attestation rules |
95
+ | **Tiered rule packs** | National (US federal guidance), regional (California) and industry (PCI DSS) starter packs |
96
+ | **Reports** | JSON, SARIF (GitHub code scanning) and HTML, in English or Simplified Chinese |
97
+ | **Agent evaluation** | Scripted multi-turn exams with tool mocks, deterministic assertions plus rubric judging, and critical-failure vetoes |
98
+ | **Pluggable adapters and judges** | OpenAI-compatible endpoints, generic webhooks and demo agents. Heuristic (offline), Anthropic or OpenAI-compatible judges |
99
+ | **Certification** | Strict gates, Ed25519-signed JSON, HTML/PDF certificates, optional QR verification URL and revocation status check |
100
+ | **CI-friendly** | Stable exit codes. No database or server required |
101
+
102
+ ## Install
103
+
104
+ Requires Python 3.11+.
105
+
106
+ ```bash
107
+ pip install "agenteval-toolkit[kubernetes]" # drop [kubernetes] if you only scan snapshots
108
+ agenteval version
109
+
110
+ mkdir my-ai-governance && cd my-ai-governance
111
+ agenteval init # copies the starter rules/, exams/, certification/ and examples/ here
112
+ ```
113
+
114
+ The PyPI package is named `agenteval-toolkit`. The command is `agenteval` and the import name is `agenteval`.
115
+ Optional extras: `pdf` (certificate PDFs through Playwright/Chromium) and `dev` (pytest and build).
116
+
117
+ The CLI looks for `rules/`, `exams/` and `certification/` in the current directory, and falls back to the
118
+ starter copies bundled with the package. Pass `--rules` or `--exams`, or set the
119
+ [environment variables](#configuration), to use other locations.
120
+
121
+ From source:
122
+
123
+ ```bash
124
+ git clone https://github.com/pony360/AgentEval.git && cd AgentEval
125
+ pip install -e ".[dev,kubernetes]"
126
+ ```
127
+
128
+ ## Quickstart
129
+
130
+ All of these commands run offline against the bundled sample cluster and demo agents.
131
+
132
+ ```bash
133
+ # 1. Validate the rule packs
134
+ agenteval rules validate
135
+ # ✓ 23 rules validated
136
+
137
+ # 2. Scan a cluster snapshot (exits 1: there are high/critical findings)
138
+ agenteval scan --snapshot examples/snapshots/sample-cluster.json -f html -o scan.html
139
+
140
+ # 3. Evaluate an agent. On a pass, also write pre-deployment-testing evidence for its asset
141
+ agenteval eval run -p cs-ecommerce-v1 -a examples/agents/demo-good.yaml -f json -o eval.json \
142
+ --attest-asset deployment/ml-prod/llama-chat --attest-output att-eval.yaml
143
+ # → 96.7 (grade A) · cases passed 10/10 · critical failures 0
144
+
145
+ # 4. Re-scan with the human attestations and the evaluation evidence
146
+ agenteval scan --snapshot examples/snapshots/sample-cluster.json \
147
+ --attestations examples/attestations.yaml \
148
+ --attestations examples/attestations-certification.yaml \
149
+ --attestations att-eval.yaml -o scan.json --fail-on none
150
+
151
+ # 5. Certify the registered system, then verify the certificate
152
+ agenteval cert keygen --public-out issuer.pem
153
+ agenteval cert issue -s northwind-cs --scan scan.json --eval eval.json -o certificates/
154
+ agenteval cert verify certificates/AEV-*.json --public-key issuer.pem
155
+ # Signature valid · State: active · DEMO certificate (heuristic judge)
156
+ ```
157
+
158
+ To scan a live cluster, run `agenteval scan --source kubernetes [--context ctx] [-n namespace]`.
159
+ It needs read-only access to Deployments, StatefulSets, Services, Ingresses and NetworkPolicies.
160
+ For air-gapped clusters, use `agenteval snapshot` to export a snapshot and scan it elsewhere.
161
+
162
+ Every command accepts `--lang zh` for Chinese output.
163
+
164
+ ## Commands and exit codes
165
+
166
+ | Command | Purpose |
167
+ |---|---|
168
+ | `agenteval init [DIR]` | Copy the starter rule packs, exams, policy and examples into a directory |
169
+ | `agenteval scan` | Collect assets and evaluate rules. Writes JSON, SARIF or HTML |
170
+ | `agenteval snapshot` | Export a read-only cluster snapshot |
171
+ | `agenteval rules validate \| list` | Validate rule packs and list rules |
172
+ | `agenteval schemas -o DIR` | Export the JSON Schemas for editors |
173
+ | `agenteval eval papers \| validate \| run` | List or validate exam papers. Run an exam against an agent |
174
+ | `agenteval cert check \| issue \| verify \| keygen` | Certification |
175
+
176
+ | Exit code | Meaning |
177
+ |---|---|
178
+ | `0` | Success, or the gate passed |
179
+ | `1` | The gate did not pass: findings at or above `--fail-on`, the exam was not passed, the system is not eligible, or the certificate is invalid |
180
+ | `2` | Usage or input error, such as an invalid rule file or a missing file |
181
+
182
+ ## Rule packs
183
+
184
+ | Pack | Tier | Rules | Covers |
185
+ |---|---|---|---|
186
+ | `us-federal` | national | 16 | NIST AI RMF 1.0, AI 600-1, SP 800-53, SP 800-190, SP 800-218A and OMB M-25-21: authentication, TLS, network policy, image pinning, secrets, provenance, governance attestations |
187
+ | `us-ca` | regional | 3 | Bot disclosure (B&P §17940), CCPA data minimization, AB 2013 training-data transparency |
188
+ | `pci-dss` | industry | 4 | PCI DSS v4.0.1 (Req. 3, 4, 8, 10): no full card numbers in logs, strong cryptography in transit, authentication, and audit logging for AI that handles payment conversations |
189
+
190
+ Rule text is in English, and Simplified Chinese translations are in `rules/*/i18n/zh.yaml`.
191
+
192
+ ## Writing rules
193
+
194
+ ```yaml
195
+ # yaml-language-server: $schema=../../agenteval/schemas/rule.schema.json
196
+ rules:
197
+ - id: FED-SEC-002
198
+ title: Externally exposed inference endpoints must use TLS
199
+ description: Services exposed through LoadBalancer, NodePort or Ingress must encrypt traffic.
200
+ severity: high
201
+ type: automated
202
+ category: data-protection
203
+ applies_to:
204
+ asset_types: [inference_service]
205
+ when: {field: exposure.public, op: eq, value: true}
206
+ check: {field: tls.enabled, op: eq, value: true}
207
+ remediation: Add a tls section to the Ingress with a trusted certificate (e.g. cert-manager).
208
+ sources:
209
+ - framework: NIST SP 800-53 Rev.5
210
+ reference: SC-8 Transmission Confidentiality and Integrity
211
+ verified: false
212
+ ```
213
+
214
+ The full reference is in **[docs/rule-schema.md](https://github.com/pony360/AgentEval/blob/main/docs/rule-schema.md)**. It covers every field,
215
+ the condition operators, the fact catalog, attestations and translations. The schemas are in
216
+ [`agenteval/schemas/`](https://github.com/pony360/AgentEval/blob/main/agenteval/schemas/).
217
+
218
+ ## Evaluating agents
219
+
220
+ An exam paper defines weighted dimensions, multi-turn cases, assertions (some of them
221
+ **critical**) and rubric items. The bundled `cs-ecommerce-v1` paper tests an e-commerce
222
+ support agent in 10 cases, from order lookup and returns to PII handling and prompt injection.
223
+
224
+ ```bash
225
+ agenteval eval run -p cs-ecommerce-v1 -a my-agent.yaml --judge anthropic --judge-model <model> \
226
+ --judge-key-env ANTHROPIC_API_KEY -o report.html
227
+ ```
228
+
229
+ See **[docs/exams.md](https://github.com/pony360/AgentEval/blob/main/docs/exams.md)** for the paper format, scoring, adapters and judges.
230
+
231
+ ## Certification
232
+
233
+ `cert issue` signs a certificate only if all of the following hold:
234
+
235
+ - the security score is **> 90** and the quality score is **> 90**,
236
+ - there are no open high or critical findings,
237
+ - no attestations are pending,
238
+ - there are no critical evaluation failures and no session errors, and
239
+ - the evidence is at most 30 days old.
240
+
241
+ Evaluations scored by the offline heuristic judge get **DEMO** certificates only. Certificates are
242
+ valid for 6 months. See **[docs/certification.md](https://github.com/pony360/AgentEval/blob/main/docs/certification.md)** for the gates, keys,
243
+ the verification URL and status hooks, and how to revoke certificates.
244
+
245
+ ## Configuration
246
+
247
+ | Variable | Default | Purpose |
248
+ |---|---|---|
249
+ | `AGENTEVAL_LANG` | `en` | Output language (`en`, `zh`) |
250
+ | `AGENTEVAL_RULES_DIR` | `./rules` | Rules directory |
251
+ | `AGENTEVAL_EXAMS_DIR` | `./exams` | Exam library |
252
+ | `AGENTEVAL_CERT_DIR` | `./certification` | Policy and system registry |
253
+ | `AGENTEVAL_SIGNING_KEY` | `./.agenteval/signing-key.pem` | Ed25519 private key |
254
+ | `AGENTEVAL_VERIFY_URL` | — | Verification URL template with `{id}` |
255
+ | `AGENTEVAL_STATUS_URL` | — | Revocation status URL template with `{id}` |
256
+ | `AGENTEVAL_JUDGE_MODEL`, `AGENTEVAL_JUDGE_BASE_URL` | — | LLM judge settings |
257
+ | `AGENTEVAL_ANNOTATION_PREFIX` | `agenteval.io/` | Kubernetes label and annotation prefix for hints |
258
+
259
+ ## Security model
260
+
261
+ - **Read-only.** The scanner only lists and reads Kubernetes objects. It never changes them.
262
+ - **No secret values.** Plaintext-secret detection records environment variable *names* only.
263
+ - **No arbitrary code.** Rule conditions are a fixed DSL, and YAML is loaded with `safe_load`.
264
+ - **Fail-closed.** Missing facts never make a check pass.
265
+ - **Secrets come from the environment.** Agent and judge API keys are read from the variables you name.
266
+ - **Private key.** The signing key is created with mode 0600 and is git-ignored.
267
+
268
+ To report a vulnerability, see [SECURITY.md](https://github.com/pony360/AgentEval/blob/main/SECURITY.md).
269
+
270
+ ## Project layout
271
+
272
+ ```
273
+ agenteval/ Python package (CLI, engine, collectors, evaluation, certification, schemas)
274
+ rules/ Rule packs (national / regional / industry)
275
+ exams/ Exam papers
276
+ certification/ Certification policy and registered systems
277
+ examples/ Sample snapshot, attestations and agent configs
278
+ docs/ Reference documentation
279
+ tests/ Test suite (pytest)
280
+ ```
281
+
282
+ ## Roadmap
283
+
284
+ - More collectors (cloud-managed endpoints, model registries, API gateways)
285
+ - More rule packs (EU AI Act, ISO/IEC 42001, HIPAA), contributed with reviewer sign-off
286
+ - More exam papers (IT helpdesk, sales assistant, RAG question answering)
287
+ - A hosted verification and status service reference implementation
288
+
289
+ ## Contributing
290
+
291
+ Contributions are welcome, especially rules, exam papers and translations. Read
292
+ [CONTRIBUTING.md](https://github.com/pony360/AgentEval/blob/main/CONTRIBUTING.md) first. Commits must be signed off under the
293
+ [DCO](https://developercertificate.org/) (`git commit -s`). This project follows the
294
+ [Code of Conduct](https://github.com/pony360/AgentEval/blob/main/CODE_OF_CONDUCT.md).
295
+
296
+ ```bash
297
+ pip install -e ".[dev]"
298
+ pytest
299
+ ```
300
+
301
+ ## License
302
+
303
+ Licensed under the [Apache License, Version 2.0](https://github.com/pony360/AgentEval/blob/main/LICENSE). See [NOTICE](https://github.com/pony360/AgentEval/blob/main/NOTICE).
304
+
305
+ Framework and regulation names, including NIST, PCI DSS and California statutes, are used
306
+ only to identify the source material a rule refers to. Their use does not imply endorsement by,
307
+ or affiliation with, their owners.
@@ -0,0 +1,67 @@
1
+ agenteval/__init__.py,sha256=tVue123DhkbYaWhVhwKRf8RpO8T6XmNfQDhfCNiGM0w,197
2
+ agenteval/cli.py,sha256=fKfmAIF8j1aHfe6xWeJHzIHz7n_fCuOoVCOOS6yf8n8,25821
3
+ agenteval/config.py,sha256=N5wCN3N8nmy8Pb4j7fN3CNkQstFLzsC6SQ0pzvjg-H4,1685
4
+ agenteval/i18n.py,sha256=4C7C3z_-Qlpu4FxyjjRHVsHl5CMdsZN0MSYiHwl477I,5980
5
+ agenteval/models.py,sha256=SOZ5yCAFYQzVwEuZ57r9q8dlNQVHRJR2yGS-rvnehRY,4064
6
+ agenteval/schema.py,sha256=k3-IdhMzKuWt3SvFVXg6SFVfXuvcEGWuaEg4koNts0M,2223
7
+ agenteval/_starter/certification/policy.yaml,sha256=HTTO1MKFpnWqVJ9OK0hOpjEUHtU9T5dgYXZgq96jTy4,1044
8
+ agenteval/_starter/certification/systems/northwind-cs-staging.yaml,sha256=qGLSi1NOn7do4o6ce3Kfqf7aqC6aIkuSRrwnKOXe9ec,786
9
+ agenteval/_starter/certification/systems/northwind-cs.yaml,sha256=ZsH4bUbeMTBcAPnwNvZMqo5gA8l65si85S2WsdUR2I4,865
10
+ agenteval/_starter/examples/attestations-certification.yaml,sha256=6nfr76tyOel4VxLoiUyxKFVNK4PoTpskndeDeBlLxkc,691
11
+ agenteval/_starter/examples/attestations.yaml,sha256=SucF6n8SmufHLs5ykkTvsimtDur6objMdWsRc6YxPJs,785
12
+ agenteval/_starter/examples/agents/demo-good.yaml,sha256=6QiZz7lJ6Rf_J59nZqFC8HOzQrzuUBNK7PRvcrGNAgY,4046
13
+ agenteval/_starter/examples/agents/demo-weak.yaml,sha256=LnQU6Dmw4T2l6RAbfLwIXWZE8yuP3UuzjCaY5bsq8LY,2316
14
+ agenteval/_starter/examples/agents/openai-compatible.example.yaml,sha256=eVTuThGScgIXnoy9oB7mT7JkGLkGgVoEEkKl1EBOCx8,827
15
+ agenteval/_starter/examples/agents/webhook.example.yaml,sha256=eBpUnu-FWL-A2vwayb88VssL03d1bwnDP5FWtO1sQR4,1018
16
+ agenteval/_starter/examples/snapshots/sample-cluster.json,sha256=VZyiMQLZRF9KbfmSYkaMR6ZsbUgluKRMsz4PKKfV6QU,7838
17
+ agenteval/_starter/exams/customer-service/cs-ecommerce-v1.yaml,sha256=5ymu0BaxknSbxtioiMuiK4_CrHXGyCdfTRqNqAOq1_M,12771
18
+ agenteval/_starter/rules/industry-pci-dss/pack.yaml,sha256=Xfqg-i70AG1HN69-wO_uTSYVzvruCfdG6RwO32FAR14,493
19
+ agenteval/_starter/rules/industry-pci-dss/rules.yaml,sha256=Wr7XM8yhByPpXlD63avjpEFlEYvv69kcP-MQq11Pah4,3559
20
+ agenteval/_starter/rules/industry-pci-dss/i18n/zh.yaml,sha256=hm2wbfwMXsFfx76eH15NklpG2Z0CjCEvHlyZ_lAVQoE,1647
21
+ agenteval/_starter/rules/us-ca/pack.yaml,sha256=4l99a7c-Fzn0eZF3_BNfUdU2aVB0hpkqE8DIPrhosNw,449
22
+ agenteval/_starter/rules/us-ca/rules.yaml,sha256=4c8sx0tdnVHJYPELTeprHTDHrtNXf0plyPZLzn0NF2A,3064
23
+ agenteval/_starter/rules/us-ca/i18n/zh.yaml,sha256=_xgm4pomajUqvVnlnTdNZThOE6FB0WI9PU_yCtO86zI,1539
24
+ agenteval/_starter/rules/us-federal/governance.yaml,sha256=ptmswMUCJkCd7LFiqo2aM3kDjFx60E1Ij8K7lUda8AM,8263
25
+ agenteval/_starter/rules/us-federal/pack.yaml,sha256=bMloa8jAE5J5XpjGmjnbn1sW6k8nGuQSWqiw_dDvqfk,336
26
+ agenteval/_starter/rules/us-federal/security.yaml,sha256=w106MMYmFExcqygzMX9befeep44ipZUEfUaw7fK9qt4,6103
27
+ agenteval/_starter/rules/us-federal/i18n/zh.yaml,sha256=x5-Pd-xjmwcBZwf3S71JvDHcUVGG6Z3DvYf1MkCgyOE,6410
28
+ agenteval/certification/__init__.py,sha256=WA_tlCBilSC2-FKKXUmLFOk91WnVMjnAGZe1MOC52Cc,904
29
+ agenteval/certification/assess.py,sha256=H9C-ysZ1PpB1CgMGiFZ6YTXNXkvwHyAZFoLpWV4q8GI,6752
30
+ agenteval/certification/issuer.py,sha256=sGkUiWZrsp1-iK2otPV3mCYiz6RQ5aAulCGi-KsVJDM,8037
31
+ agenteval/certification/models.py,sha256=aWItVp_39_YtFF1TUQGcItVInH9eLCE5Rzb-kxhpa7I,3537
32
+ agenteval/certification/render.py,sha256=0vdNIL5pg_RBtUNavI_zdaa_51aYN07x9YVg9xPHsKs,6264
33
+ agenteval/certification/signing.py,sha256=aNkStfS37j-EHZZlRpxU3wgTt4SBJSRNszL1QOOSQro,3279
34
+ agenteval/collectors/__init__.py,sha256=IUSSaMLURDOF43m3mtA2I_Lh5hObalr1YkZuWbPj4OI,1187
35
+ agenteval/collectors/kubernetes.py,sha256=tvG8wL-OS0_XKbYXVPx7PBu4RU3CcyFLn7RhizcIAPM,2635
36
+ agenteval/collectors/normalize.py,sha256=OD3_3L07W801i1QvCmThUxhsNhZK3zXSbKMbTs_N--g,10851
37
+ agenteval/engine/__init__.py,sha256=4cpjYVNRepOtcsbyvN5fuJWI28X5YI237w_Y9YHlx1o,435
38
+ agenteval/engine/conditions.py,sha256=Rz0jK7WY5qn8F7RU_dDin-prLp6hWi1DUjbXnwnE1DM,3642
39
+ agenteval/engine/evaluator.py,sha256=7f5vKfn7nFdUDrkkNwyE609BZuRVq1yN2OxGnodv3J4,6042
40
+ agenteval/engine/loader.py,sha256=fSnxz75iJ1eKvo0FPi63Xxzb3OMf2jmQ_eCp-l1fCOw,4500
41
+ agenteval/evaluation/__init__.py,sha256=EASMkG1rXs4DAHFLPLl1XObaHBwD0agcAdn9VkE3BAk,733
42
+ agenteval/evaluation/adapters.py,sha256=iyET8647hF9_6N_bbcpcHMl2p0YHJWnGJVyfgNszpSw,10448
43
+ agenteval/evaluation/assertions.py,sha256=H-1CpXCKw5LzbO8vArugjzAgHsQ-G5ZcVh9AkHjLNDQ,2896
44
+ agenteval/evaluation/judges.py,sha256=YO7pEqFjXytQr6hEjugQJWM-zxZSQJEM00jkfND_BtE,9587
45
+ agenteval/evaluation/messages.py,sha256=qqLY12JDMNGq4dTuafGpruVj2pGHsLl61J5l13tAU34,3128
46
+ agenteval/evaluation/models.py,sha256=6qpe0ZuQg84rM5Y64XD7WmO2L8UyyVDu48IGJVKrqP4,4888
47
+ agenteval/evaluation/papers.py,sha256=BNmNcyx7kUhM9tNUV1ssxRNOXEvWt4SZYc8THZwa-yc,3751
48
+ agenteval/evaluation/report.py,sha256=J5k5xFXEIu9DB4v1OcsYZiVS2wCsVN0xJRLFuHCSKtY,4370
49
+ agenteval/evaluation/runner.py,sha256=7u48DWaVya2XsIhD-NYcm550Rxf-sgKgAsBpnUsLTwM,7392
50
+ agenteval/reports/__init__.py,sha256=-TXA5RMW8B8idYII-eXtO8E90lh5757rW7Ojw5SUe8Y,3366
51
+ agenteval/reports/templates/certificate.html.j2,sha256=qZo088YTwN5wXUJwffjUFgfqTR6Kgv7vsP1oyDfuSKY,11220
52
+ agenteval/reports/templates/eval_report.html.j2,sha256=MLJonT6r_nPgOaypLSaNZ4KhZRk7Ts8ZxW_xpvncn0c,10868
53
+ agenteval/reports/templates/report.html.j2,sha256=EU9IJgyoV1sWlybJQFu9M5TOue7AQODbgju4WfgvFkg,3680
54
+ agenteval/schemas/attestations.schema.json,sha256=7CL5N6PjFIU9d5DsxJXRE7OMVg2XVlK611LgYjXtBb8,1862
55
+ agenteval/schemas/exam.schema.json,sha256=6MQuUSzNaGb4RUf2PWr4RpP-_cEWixHQMo_rnhQfh4Q,3449
56
+ agenteval/schemas/pack.schema.json,sha256=J5KlaWedgReKDW_k5B-_RXwR3-X9SfkEmBJBDGqiFOM,1157
57
+ agenteval/schemas/policy.schema.json,sha256=1RmhysL1rh1P6FJkNt2YRwTcWozXryI8D3v4BjCsID0,1529
58
+ agenteval/schemas/rule.schema.json,sha256=qYzaY_jYc3Dm_LA7c6EbXWMv0WmQtS_c-TXCJbnak58,7664
59
+ agenteval/schemas/system.schema.json,sha256=6gDVjRdhNGKpc7UpCtydUNCIQ8ldLaU5HPcgszdYW9g,1653
60
+ agenteval/schemas/translations.schema.json,sha256=LkFOjA9SOdEWPE2-Zkx1jsdyPvE7klv8tfztsSNPK9g,798
61
+ agenteval_toolkit-0.1.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
62
+ agenteval_toolkit-0.1.0.dist-info/licenses/NOTICE,sha256=q9oPgTrZP4HK4uNxbfP5rVDv7Tap-ygvqvvp-9AM_rE,891
63
+ agenteval_toolkit-0.1.0.dist-info/METADATA,sha256=QMyIg7UEKhB6VWX7Rh5uer4zRAxtcQ37HY8ji0WmDKU,14168
64
+ agenteval_toolkit-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
65
+ agenteval_toolkit-0.1.0.dist-info/entry_points.txt,sha256=0QlEVPc-qpGl_N2iL0YY31_BjOxvlffpBbYKxff9BFg,48
66
+ agenteval_toolkit-0.1.0.dist-info/top_level.txt,sha256=k6izISLxVoNnLxZHqnS3X-0eDdUD8LsV-OoM0afYdew,10
67
+ agenteval_toolkit-0.1.0.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: setuptools (84.0.0)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1,2 @@
1
+ [console_scripts]
2
+ agenteval = agenteval.cli:app
@@ -0,0 +1,202 @@
1
+
2
+ Apache License
3
+ Version 2.0, January 2004
4
+ http://www.apache.org/licenses/
5
+
6
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
7
+
8
+ 1. Definitions.
9
+
10
+ "License" shall mean the terms and conditions for use, reproduction,
11
+ and distribution as defined by Sections 1 through 9 of this document.
12
+
13
+ "Licensor" shall mean the copyright owner or entity authorized by
14
+ the copyright owner that is granting the License.
15
+
16
+ "Legal Entity" shall mean the union of the acting entity and all
17
+ other entities that control, are controlled by, or are under common
18
+ control with that entity. For the purposes of this definition,
19
+ "control" means (i) the power, direct or indirect, to cause the
20
+ direction or management of such entity, whether by contract or
21
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
22
+ outstanding shares, or (iii) beneficial ownership of such entity.
23
+
24
+ "You" (or "Your") shall mean an individual or Legal Entity
25
+ exercising permissions granted by this License.
26
+
27
+ "Source" form shall mean the preferred form for making modifications,
28
+ including but not limited to software source code, documentation
29
+ source, and configuration files.
30
+
31
+ "Object" form shall mean any form resulting from mechanical
32
+ transformation or translation of a Source form, including but
33
+ not limited to compiled object code, generated documentation,
34
+ and conversions to other media types.
35
+
36
+ "Work" shall mean the work of authorship, whether in Source or
37
+ Object form, made available under the License, as indicated by a
38
+ copyright notice that is included in or attached to the work
39
+ (an example is provided in the Appendix below).
40
+
41
+ "Derivative Works" shall mean any work, whether in Source or Object
42
+ form, that is based on (or derived from) the Work and for which the
43
+ editorial revisions, annotations, elaborations, or other modifications
44
+ represent, as a whole, an original work of authorship. For the purposes
45
+ of this License, Derivative Works shall not include works that remain
46
+ separable from, or merely link (or bind by name) to the interfaces of,
47
+ the Work and Derivative Works thereof.
48
+
49
+ "Contribution" shall mean any work of authorship, including
50
+ the original version of the Work and any modifications or additions
51
+ to that Work or Derivative Works thereof, that is intentionally
52
+ submitted to Licensor for inclusion in the Work by the copyright owner
53
+ or by an individual or Legal Entity authorized to submit on behalf of
54
+ the copyright owner. For the purposes of this definition, "submitted"
55
+ means any form of electronic, verbal, or written communication sent
56
+ to the Licensor or its representatives, including but not limited to
57
+ communication on electronic mailing lists, source code control systems,
58
+ and issue tracking systems that are managed by, or on behalf of, the
59
+ Licensor for the purpose of discussing and improving the Work, but
60
+ excluding communication that is conspicuously marked or otherwise
61
+ designated in writing by the copyright owner as "Not a Contribution."
62
+
63
+ "Contributor" shall mean Licensor and any individual or Legal Entity
64
+ on behalf of whom a Contribution has been received by Licensor and
65
+ subsequently incorporated within the Work.
66
+
67
+ 2. Grant of Copyright License. Subject to the terms and conditions of
68
+ this License, each Contributor hereby grants to You a perpetual,
69
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
70
+ copyright license to reproduce, prepare Derivative Works of,
71
+ publicly display, publicly perform, sublicense, and distribute the
72
+ Work and such Derivative Works in Source or Object form.
73
+
74
+ 3. Grant of Patent License. Subject to the terms and conditions of
75
+ this License, each Contributor hereby grants to You a perpetual,
76
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
+ (except as stated in this section) patent license to make, have made,
78
+ use, offer to sell, sell, import, and otherwise transfer the Work,
79
+ where such license applies only to those patent claims licensable
80
+ by such Contributor that are necessarily infringed by their
81
+ Contribution(s) alone or by combination of their Contribution(s)
82
+ with the Work to which such Contribution(s) was submitted. If You
83
+ institute patent litigation against any entity (including a
84
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
85
+ or a Contribution incorporated within the Work constitutes direct
86
+ or contributory patent infringement, then any patent licenses
87
+ granted to You under this License for that Work shall terminate
88
+ as of the date such litigation is filed.
89
+
90
+ 4. Redistribution. You may reproduce and distribute copies of the
91
+ Work or Derivative Works thereof in any medium, with or without
92
+ modifications, and in Source or Object form, provided that You
93
+ meet the following conditions:
94
+
95
+ (a) You must give any other recipients of the Work or
96
+ Derivative Works a copy of this License; and
97
+
98
+ (b) You must cause any modified files to carry prominent notices
99
+ stating that You changed the files; and
100
+
101
+ (c) You must retain, in the Source form of any Derivative Works
102
+ that You distribute, all copyright, patent, trademark, and
103
+ attribution notices from the Source form of the Work,
104
+ excluding those notices that do not pertain to any part of
105
+ the Derivative Works; and
106
+
107
+ (d) If the Work includes a "NOTICE" text file as part of its
108
+ distribution, then any Derivative Works that You distribute must
109
+ include a readable copy of the attribution notices contained
110
+ within such NOTICE file, excluding those notices that do not
111
+ pertain to any part of the Derivative Works, in at least one
112
+ of the following places: within a NOTICE text file distributed
113
+ as part of the Derivative Works; within the Source form or
114
+ documentation, if provided along with the Derivative Works; or,
115
+ within a display generated by the Derivative Works, if and
116
+ wherever such third-party notices normally appear. The contents
117
+ of the NOTICE file are for informational purposes only and
118
+ do not modify the License. You may add Your own attribution
119
+ notices within Derivative Works that You distribute, alongside
120
+ or as an addendum to the NOTICE text from the Work, provided
121
+ that such additional attribution notices cannot be construed
122
+ as modifying the License.
123
+
124
+ You may add Your own copyright statement to Your modifications and
125
+ may provide additional or different license terms and conditions
126
+ for use, reproduction, or distribution of Your modifications, or
127
+ for any such Derivative Works as a whole, provided Your use,
128
+ reproduction, and distribution of the Work otherwise complies with
129
+ the conditions stated in this License.
130
+
131
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
132
+ any Contribution intentionally submitted for inclusion in the Work
133
+ by You to the Licensor shall be under the terms and conditions of
134
+ this License, without any additional terms or conditions.
135
+ Notwithstanding the above, nothing herein shall supersede or modify
136
+ the terms of any separate license agreement you may have executed
137
+ with Licensor regarding such Contributions.
138
+
139
+ 6. Trademarks. This License does not grant permission to use the trade
140
+ names, trademarks, service marks, or product names of the Licensor,
141
+ except as required for reasonable and customary use in describing the
142
+ origin of the Work and reproducing the content of the NOTICE file.
143
+
144
+ 7. Disclaimer of Warranty. Unless required by applicable law or
145
+ agreed to in writing, Licensor provides the Work (and each
146
+ Contributor provides its Contributions) on an "AS IS" BASIS,
147
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148
+ implied, including, without limitation, any warranties or conditions
149
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150
+ PARTICULAR PURPOSE. You are solely responsible for determining the
151
+ appropriateness of using or redistributing the Work and assume any
152
+ risks associated with Your exercise of permissions under this License.
153
+
154
+ 8. Limitation of Liability. In no event and under no legal theory,
155
+ whether in tort (including negligence), contract, or otherwise,
156
+ unless required by applicable law (such as deliberate and grossly
157
+ negligent acts) or agreed to in writing, shall any Contributor be
158
+ liable to You for damages, including any direct, indirect, special,
159
+ incidental, or consequential damages of any character arising as a
160
+ result of this License or out of the use or inability to use the
161
+ Work (including but not limited to damages for loss of goodwill,
162
+ work stoppage, computer failure or malfunction, or any and all
163
+ other commercial damages or losses), even if such Contributor
164
+ has been advised of the possibility of such damages.
165
+
166
+ 9. Accepting Warranty or Additional Liability. While redistributing
167
+ the Work or Derivative Works thereof, You may choose to offer,
168
+ and charge a fee for, acceptance of support, warranty, indemnity,
169
+ or other liability obligations and/or rights consistent with this
170
+ License. However, in accepting such obligations, You may act only
171
+ on Your own behalf and on Your sole responsibility, not on behalf
172
+ of any other Contributor, and only if You agree to indemnify,
173
+ defend, and hold each Contributor harmless for any liability
174
+ incurred by, or claims asserted against, such Contributor by reason
175
+ of your accepting any such warranty or additional liability.
176
+
177
+ END OF TERMS AND CONDITIONS
178
+
179
+ APPENDIX: How to apply the Apache License to your work.
180
+
181
+ To apply the Apache License to your work, attach the following
182
+ boilerplate notice, with the fields enclosed by brackets "[]"
183
+ replaced with your own identifying information. (Don't include
184
+ the brackets!) The text should be enclosed in the appropriate
185
+ comment syntax for the file format. We also recommend that a
186
+ file or class name and description of purpose be included on the
187
+ same "printed page" as the copyright notice for easier
188
+ identification within third-party archives.
189
+
190
+ Copyright [yyyy] [name of copyright owner]
191
+
192
+ Licensed under the Apache License, Version 2.0 (the "License");
193
+ you may not use this file except in compliance with the License.
194
+ You may obtain a copy of the License at
195
+
196
+ http://www.apache.org/licenses/LICENSE-2.0
197
+
198
+ Unless required by applicable law or agreed to in writing, software
199
+ distributed under the License is distributed on an "AS IS" BASIS,
200
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
201
+ See the License for the specific language governing permissions and
202
+ limitations under the License.
@@ -0,0 +1,19 @@
1
+ AgentEval
2
+ Copyright 2026 The AgentEval Authors
3
+
4
+ This product includes software developed by The AgentEval Authors and is
5
+ licensed under the Apache License, Version 2.0 (see LICENSE).
6
+
7
+ Rule packs, exam papers and certification policies in this repository are
8
+ technical starter content. Rule-to-regulation mappings are provided for
9
+ convenience, are marked "verified: false" until reviewed, and do not
10
+ constitute legal advice or a determination of regulatory compliance.
11
+
12
+ Names of frameworks, standards and regulations (including NIST publications,
13
+ PCI DSS, and California statutes) are used nominatively to identify source
14
+ material. PCI DSS is a standard of the PCI Security Standards Council, LLC.
15
+ No endorsement by or affiliation with any standards body or regulator is
16
+ implied.
17
+
18
+ "Northwind Outfitters" and all example organizations, hosts and data in the
19
+ examples/ directory are fictional.
@@ -0,0 +1 @@
1
+ agenteval